Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to iconic cultural phenomena and their influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âng
    -0.17
     åĭ
    -0.16
     Verd
    -0.16
    wort
    -0.15
    olin
    -0.14
     hood
    -0.14
    duino
    -0.14
     Clay
    -0.14
    ách
    -0.14
    PLUGIN
    -0.14
    POSITIVE LOGITS
     Sex
    0.30
    Sex
    0.23
     SAT
    0.22
     Sexo
    0.21
     Manhattan
    0.21
    SAT
    0.20
     sex
    0.20
     HBO
    0.19
     SEX
    0.19
     Carrie
    0.19
    Act Density 0.016%

    No Known Activations